Lossless Compression of Structured Convolutional Models via LiftingDownload PDF

Published: 12 Jan 2021, Last Modified: 22 Oct 2023ICLR 2021 PosterReaders: Everyone
Keywords: weight sharing, graph neural networks, lifted inference, relational learning, dynamic computation graphs, convolutional models
Abstract: Lifting is an efficient technique to scale up graphical models generalized to relational domains by exploiting the underlying symmetries. Concurrently, neural models are continuously expanding from grid-like tensor data into structured representations, such as various attributed graphs and relational databases. To address the irregular structure of the data, the models typically extrapolate on the idea of convolution, effectively introducing parameter sharing in their, dynamically unfolded, computation graphs. The computation graphs themselves then reflect the symmetries of the underlying data, similarly to the lifted graphical models. Inspired by lifting, we introduce a simple and efficient technique to detect the symmetries and compress the neural models without loss of any information. We demonstrate through experiments that such compression can lead to significant speedups of structured convolutional models, such as various Graph Neural Networks, across various tasks, such as molecule classification and knowledge-base completion.
One-sentence Summary: Speeding up weight-sharing dynamic neural computation graphs, such as GNNs, with lifted inference.
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
Supplementary Material: zip
Code: [![github](/images/github_icon.svg) GustikS/NeuraLogic](https://github.com/GustikS/NeuraLogic) + [![Papers with Code](/images/pwc_icon.svg) 1 community implementation](https://paperswithcode.com/paper/?openreview=oxnp2q-PGL4)
Community Implementations: [![CatalyzeX](/images/catalyzex_icon.svg) 2 code implementations](https://www.catalyzex.com/paper/arxiv:2007.06567/code)
9 Replies